Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to boundaries and limits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     jLabel
    -0.88
    insatz
    -0.77
     Pfer
    -0.76
     pluie
    -0.76
     فريبيس
    -0.76
    IsMutable
    -0.76
     Kakashi
    -0.73
     Shetty
    -0.73
     egret
    -0.72
    Dosage
    -0.72
    POSITIVE LOGITS
    bounds
    1.32
    Bounds
    1.22
     bounds
    1.22
     Bound
    1.21
     BOUND
    1.16
     Bounds
    1.14
    BOUND
    1.12
     bound
    1.10
     Boun
    1.07
    Bound
    1.07
    Act Density 0.116%

    No Known Activations